使用比例参数训练 Caffe CNN

【问题标题】：Train a Caffe CNN with Scale Parameter使用比例参数训练 Caffe CNN
【发布时间】：2018-07-01 06:45:56
【问题描述】：

我已经修改了 bvlc_reference_caffenet 中的 train_val.prototxt 以在 Caffe 中实现 VGG-16 克隆，并且能够使用带有 batch_size: 6 和 base_lr: 0.0648 (~ 0.01 * sqrt(256/6) ~ 0.01 * sqrt(42)) 的 GTX 1050 对其进行训练。但是，我想将输入数据从 [0;255] 缩放到 [0;1]，因为这个 CNN 的目标平台的准确度有限。为了缩放数据，我引入了scale: 0.00390625 参数（取自在目标平台上运行良好的 Caffe LeNet 示例）。但是使用scale 参数，准确度不会增加（> 40000 次迭代），并且损失在训练期间也不会改变。

如何使用 scale 参数训练这个 CNN？

train_val.prototxt

name: "ES VGG"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
    mirror: true
    crop_size: 224
    mean_file: "/local/datasets/imagenet/ilsvrc12/imagenet_mean.binaryproto"
  }
  data_param {
    source: "/local/datasets/imagenet/ilsvrc12_train_lmdb"
    batch_size: 6
    backend: LMDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
    mirror: false
    crop_size: 224
    mean_file: "/local/datasets/imagenet/ilsvrc12/imagenet_mean.binaryproto"
  }
  data_param {
    source: "/local/datasets/imagenet/ilsvrc12_val_lmdb"
    batch_size: 6
    backend: LMDB
  }
}
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "data"
  top: "conv1_1"
  convolution_param {
    num_output: 64
    kernel_size: 3
    pad: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1_1"
  type: "ReLU"
  bottom: "conv1_1"
  top: "conv1_1"
}
layer {
  name: "conv1_2"
  type: "Convolution"
  bottom: "conv1_1"
  top: "conv1_2"
  convolution_param {
    num_output: 64
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1_2"
  type: "ReLU"
  bottom: "conv1_2"
  top: "conv1_2"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1_2"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2_1"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2_1"
  convolution_param {
    num_output: 128
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_1"
  type: "ReLU"
  bottom: "conv2_1"
  top: "conv2_1"
}
layer {
  name: "conv2_2"
  type: "Convolution"
  bottom: "conv2_1"
  top: "conv2_2"
  convolution_param {
    num_output: 128
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_2"
  type: "ReLU"
  bottom: "conv2_2"
  top: "conv2_2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2_2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3_1"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3_1"
  convolution_param {
    num_output: 256
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_1"
  type: "ReLU"
  bottom: "conv3_1"
  top: "conv3_1"
}
layer {
  name: "conv3_2"
  type: "Convolution"
  bottom: "conv3_1"
  top: "conv3_2"
  convolution_param {
    num_output: 256
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_2"
  type: "ReLU"
  bottom: "conv3_2"
  top: "conv3_2"
}
layer {
  name: "conv3_3"
  type: "Convolution"
  bottom: "conv3_2"
  top: "conv3_3"
  convolution_param {
    num_output: 256
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_3"
  type: "ReLU"
  bottom: "conv3_3"
  top: "conv3_3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3_3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4_1"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4_1"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_1"
  type: "ReLU"
  bottom: "conv4_1"
  top: "conv4_1"
}
layer {
  name: "conv4_2"
  type: "Convolution"
  bottom: "conv4_1"
  top: "conv4_2"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_2"
  type: "ReLU"
  bottom: "conv4_2"
  top: "conv4_2"
}
layer {
  name: "conv4_3"
  type: "Convolution"
  bottom: "conv4_2"
  top: "conv4_3"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_3"
  type: "ReLU"
  bottom: "conv4_3"
  top: "conv4_3"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4_3"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv5_1"
  type: "Convolution"
  bottom: "pool4"
  top: "conv5_1"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu5_1"
  type: "ReLU"
  bottom: "conv5_1"
  top: "conv5_1"
}
layer {
  name: "conv5_2"
  type: "Convolution"
  bottom: "conv5_1"
  top: "conv5_2"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu5_2"
  type: "ReLU"
  bottom: "conv5_2"
  top: "conv5_2"
}
layer {
  name: "conv5_3"
  type: "Convolution"
  bottom: "conv5_2"
  top: "conv5_3"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5_3"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  inner_product_param {
    num_output: 4096
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.01
    }
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  inner_product_param {
    num_output: 4096
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.01
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc8"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8"
  inner_product_param {
    num_output: 1000
    weight_filler {
    type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.01
    }
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8"
  bottom: "label"
  top: "loss"
}
layer {
  name: "accuracytop1"
  type: "Accuracy"
  bottom: "fc8"
  bottom: "label"
  top: "accuracytop1"
  accuracy_param {
    top_k: 1
  }
  include {
    phase: TEST
  }
}
layer {
  name: "accuracytop5"
  type: "Accuracy"
  bottom: "fc8"
  bottom: "label"
  top: "accuracytop5"
  accuracy_param {
    top_k: 5
  }
  include {
    phase: TEST
  }
}

solver.prototxt

net: "models/es_vgg/train_val.prototxt"
test_iter: 1000
test_interval: 1000
base_lr: 0.0648
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 18900000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/es_vgg/es_vgg_train"
solver_mode: GPU

【问题讨论】：

    标签： machine-learning neural-network computer-vision deep-learning caffe


    【解决方案1】：

    如果您将输入除以255，则需要将第一个卷积层"conv1_1" 的权重乘以255 以补偿这种变化。
    查看net surgery 了解如何做到这一点。

    例如（在python中）：

    import caffe
net = caffe.Net('models/es_vgg/train_val.prototxt', caffe.TEST)  # no .caffemodel weights supplied - weights are randomly init
# scale kernels of first conv layer by 255
net.params['conv1_1'][0].data[...] = 255. * net.params['conv1_1'][0].data
# save the scaled weights
net.save('models/es_vgg/init_scaled.caffemodel')

    现在您需要使用'models/es_vgg/init_scaled.caffemodel' 开始您的培训。

    【讨论】：

    • 在我看来，网络手术是在我训练完模型后完成的？
    • @konze 如果你微调，那么你可以对预训练的权重进行净手术。如果你训练房间从头开始，你只需要缩放 weight_filler
    • 我仍然不确定 net-surgery 的作用以及它如何帮助我使用带有 [0;1] 而不是 [0;255] 的 CNN？由于我使用 Xavier 作为填充物，我无法调整体重。我应该使用其他填充物吗？
    • @konze 您可以在随机初始化后进行网络手术，也可以使用带有缩放标准的高斯填充物
    • 再一次，我不明白网络手术的用途以及我应该如何使用它。您提供的链接 (github.com/BVLC/caffe/blob/master/examples/net_surgery.ipynb) 似乎没有解决我的问题。你能给我一个更广泛的例子来解决我的问题吗？
    猜你喜欢
    • 1970-01-01
    • 2018-12-16
    • 1970-01-01
    • 2015-10-15
    • 1970-01-01
    • 1970-01-01
    • 2017-04-20
    • 2016-08-23
    • 1970-01-01
    相关资源
    最近更新 更多
    热门标签
    Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode